Mao Weijia
Mao Weijia
actually i have met the same problem. I think we can put the tensor to gpu to solve the problem. It is because the cpu resource is too tight. `...
We initially suspected that RL might be the cause of the issue. Could you confirm whether our SFT results are within the expected range? We compared our results with the...
Thanks. But I have one more question: the result from the Industrial_and_Scientific dataset? In Figure 1 of the paper, the HR@10 after SFT is below 0.14, about 0.135, but your...